Skills
skills/skillssh/skills/speech-to-text/Gen Agent Trust Hub

speech-to-text

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill refers to an external installation script for the belt CLI hosted on GitHub (inference-sh/skills) and suggests adding related skills via npx.
  • [COMMAND_EXECUTION]: The skill uses the belt command-line interface to perform authentication and run transcription tasks via the Bash tool.
  • [PROMPT_INJECTION]: The skill exhibits a surface area for indirect prompt injection by processing untrusted audio and video data from remote URLs.
  • Ingestion points: The audio_url and video_url parameters in the belt app run commands.
  • Boundary markers: No explicit delimiters or instructions are provided to the model to ignore potential instructions embedded within the resulting transcriptions.
  • Capability inventory: The skill has access to the Bash tool, though it is scoped specifically to the belt command.
  • Sanitization: No sanitization or validation of the input audio content or output transcription text is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 10:50 AM
Security Audit — agent-trust-hub — speech-to-text